Triple

T20051388
Position Surface form Disambiguated ID Type / Status
Subject Garioch E499207 entity
Predicate hasSettlement P1068 FINISHED
Object Oldmeldrum NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Oldmeldrum | Statement: [Garioch, hasSettlement, Oldmeldrum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Oldmeldrum
Context triple: [Garioch, hasSettlement, Oldmeldrum]
  • A. Oldmeldrum chosen
    Oldmeldrum is a small historic town in Aberdeenshire, Scotland, known for its whisky distillery and agricultural heritage.
  • B. Barholm
    Barholm is a small village and civil parish in Lincolnshire, England, known for its rural character and historic parish church.
  • C. Sallands
    Sallands is a Dutch Low Saxon dialect spoken in the Salland region of the province of Overijssel in the Netherlands.
  • D. Molendinar
    Molendinar is a suburb in the City of Gold Coast, Queensland, Australia, known for its mix of residential areas and light industrial and commercial precincts.
  • E. Dunkeld
    Dunkeld is a historic town in Perth and Kinross, Scotland, known for its picturesque setting on the River Tay and its medieval cathedral.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69da6276bcf48190aabbf279192a5fb4 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6632ee4d48190b9de3a1efa064492 completed April 20, 2026, 5:32 p.m.
Created at: April 11, 2026, 3:38 p.m.